检索结果-内蒙古大学图书馆

Improving ASTRO's Perception Capability for a more Natural Follow-Me Task 6

学校读者我要写书评

暂无评论

Improving ASTRO's Perception Capability for a more Natural F...

6th Experiment at International Conference, exp.at 2023

作者： Ferreira, Bruno Sorrentino, Alessandra Menezes, Paulo Batista, Jorge Dias, Jorge Fiorini, Laura Cavallo, Filipo University of Coimbra Institute of Systems and Robotics Dept. of Electrical and Computer Engineering Coimbra Portugal Khalifa University of Science and Technology Khalifa University Center for Autonomous Robotic Systems Abu Dhabi United Arab Emirates University of Florence Dept. of Industrial Engineering Florence Italy BioRobotics Institute Scuola Superiore Sant'Anna Pisa Italy

ISBN: (纸本)9798350314403

Social assistive robots usually encompass a great compromise between the advanced perception models that one can use and their computing capabilities. The ideal approaches are always oriented towards low power consumption while maintaining a higher order of responsiveness to the surroundings. Therefore, we present in this paper, an improvement of the follow-me system on ASTRO. In detail, we propose the use of Mediapipe SDK for human detection and tracking, when ASTRO is meant to accompany someone that is walking. A study on the new velocity and distance profiles that the robot keeps from the individuals is presented and we have also evaluated how it affects their perception of being safe. The presented results show that our new approach allows the system to achieve real-time performance by becoming ≈ 9.1× faster, smoothing, and keeping a more natural distance from the user. © 2023 IEEE.

关键词： Human robot interaction

Sharp analysis of out-of-distribution error for "importance-weighted" estimators in the overparameterized regime

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lai, Kuo-Wei Muthukumar, Vidya School of Electrical & Computer Engineering Georgia Institute of Technology United States H. Milton School of Industrial & Systems Engineering Georgia Institute of Technology United States

Overparameterized models that achieve zero training error are observed to generalize well on average, but degrade in performance when faced with data that is under-represented in the training sample. In this work, we study an overparameterized Gaussian mixture model imbued with a spurious feature, and sharply analyze the in-distribution and out-of-distribution test error of a cost-sensitive interpolating solution that incorporates "importance weights". Compared to recent work [1, 27], our analysis is sharp with matching upper and lower bounds, and significantly weakens required assumptions on data dimensionality. Our error characterizations also apply to any choice of importance weights and unveil a novel tradeoff between worst-case robustness to distribution shift and average accuracy as a function of the importance weight magnitude1. Copyright © 2024, The Authors. All rights reserved.

关键词： Errors

Implantable UWB Microstrip Patch Antenna for Biomedical Applications

学校读者我要写书评

暂无评论

Implantable UWB Microstrip Patch Antenna for Biomedical Appl...

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： Sadman Ishraq Md Al Imran Khorshed Alam Mohammad Monirujjaman Khan Department of Electrical and Computer Engineering North South University Dhaka Bangladesh Phillip M. Drayer Department of Electrical Engineering Lamar University Texas USA Industrial and Systems Engineering Department Lamar University Texas USA

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530020

To satisfy the requirements of UWB (3.1-10.6 GHz), a novel implanted ultra-wideband (UWB) antenna with a frequency range of 3.07-13.7 GHz has been developed, targeting biomedical applications. The antenna's performance was analyzed at 4 GHz, 6 GHz, 8 GHz, and 10 GHz in both in-body and free-space environments to ensure optimal functionality. The primary focus of the design is to create a compact, cost-effective, and high-performance antenna tailored for medical and healthcare applications. The radiating element consists of a rectangular patch fabricated on an FR-4 substrate, with total dimensions of $30\times 27\times 1.6\ \text{mm}^{3}$ . A partial ground plane is incorporated to achieve ultra-wideband characteristics, enabling a 10.63 GHz bandwidth that spans frequencies from 3.07 GHz to 13.7 GHz in open space. To evaluate the antenna's performance under implantation conditions, three human tissue layers are incorporated into the design. Key features such as radiation characteristics, gain, and directivity validate its suitability for use within the human body. The entire design process, including simulations and performance evaluations, was carried out using the CST Studio Suite software.

关键词： Microstrip antennas Medical services Bandwidth Ultra wideband antennas Specific absorption rate Software Safety Microstrip Substrates Antenna radiation patterns

Contrast enhancement of optical videoscope images

学校读者我要写书评

暂无评论

Iran Journal of computer Science 2023年第3期6卷 261-275页

作者： Ammar, Reda Aboshosha, Sahar El-Hag, Noha A. Saifeldeen, Reda El-Shafai, Walid El-Banby, Ghada M. Ashiba, Huda I. Khalaf, Ashraf A. M. Elazm, Atef Abou El-Rabaie, El-Sayed M. Abd El-Samie, Fathi E. El-Safrawey, Amir Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf 32952 Egypt Department of Electronics and Electrical Comm. Faculty of Engineering Minia University Minya Egypt Department of Management of Information Systems Higher Institute of Commercial Science El-Mahala El-Kobra Egypt Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menouf 32952 Egypt Department of Electronics and Electrical Communications Engineering Bilbis Higher Institute of Engineering Sharqia Bilbis Egypt Security Engineering Laboratory Computer Science Department Prince Sultan University Riyadh 11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh 11671 Saudi Arabia

The videoscope (VS) images have poor quality and low contrast. Hence, in this paper, three proposed frameworks to improve the quality of VS images are presented. The first framework depends on contrast-limited adaptive histogram equalization (CLAHE) with adaptive gamma correction. The second framework depends on homomorphic processing. The third framework is based on the homomorphic enhancement with histogram equalization. The first one is superior from the entropy perspective, while the third one is superior from the contrast perspective. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2023.

关键词： Fuzzy enhancement Histogram equalization Homomorphic enhancement Spectral entropy

Safe Gradient Flow for Bilevel Optimization

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Sharifi, Sina Abolfazli, Nazanin Hamedani, Erfan Yazdandoost Fazlyab, Mahyar Department of Electrical and Computer Engineering Johns Hopkins University BaltimoreMD21218 United States Department of Systems and Industrial Engineering The University of Arizona TucsonAZ85721 United States

Bilevel optimization is a key framework in hierarchical decision-making, where one problem is embedded within the constraints of another. In this work, we propose a control-theoretic approach to solving bilevel optimization problems. Our method consists of two components: a gradient flow mechanism to minimize the upper-level objective and a safety filter to enforce the constraints imposed by the lower-level problem. Together, these components form a safe gradient flow that solves the bilevel problem in a single loop. To improve scalability with respect to the lower-level problem’s dimensions, we introduce a relaxed formulation and design a compact variant of the safe gradient flow. This variant minimizes the upper-level objective while ensuring the lower-level decision variable remains within a user-defined suboptimality. Using Lyapunov analysis, we establish convergence guarantees for the dynamics, proving that they converge to a neighborhood of the optimal solution. Numerical experiments further validate the effectiveness of the proposed approaches. Our contributions provide both theoretical insights and practical tools for efficiently solving bilevel optimization problems. Copyright © 2025, The Authors. All rights reserved.

关键词： Control theory

On Partial Optimal Transport: Revising the Infeasibility of Sinkhorn and Efficient Gradient Methods 38

学校读者我要写书评

暂无评论

On Partial Optimal Transport: Revising the Infeasibility of ...

38th AAAI Conference on Artificial Intelligence, AAAI 2024

作者： Nguyen, Anh Duc Nguyen, Tuan Dung Nguyen, Quang Minh Nguyen, Hoang H. Nguyen, Lam M. Toh, Kim-Chuan Department of Mathematics National University of Singapore Singapore Department of Computer and Information Science University of Pennsylvania United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology United States School of Industrial and Systems Engineering Georgia Institute of Technology United States IBM Research Thomas J. Watson Research Center United States Institute of Operations Research and Analytics National University of Singapore Singapore

ISBN: (纸本)1577358872

This paper studies the Partial Optimal Transport (POT) problem between two unbalanced measures with at most n supports and its applications in various AI tasks such as color transfer or domain adaptation. There is hence a need for fast approximations of POT with increasingly large problem sizes in arising applications. We first theoretically and experimentally investigate the infeasibility of the state-of-the-art Sinkhorn algorithm for POT, which consequently degrades its qualitative performance in real world applications like point-cloud registration. To this end, we propose a novel rounding algorithm for POT, and then provide a feasible Sinkhorn procedure with a revised computation complexity of Oe(n2/Ε4). Our rounding algorithm also permits the development of two first-order methods to approximate the POT problem. The first algorithm, Adaptive Primal-Dual Accelerated Gradient Descent (APDAGD), finds an Ε-approximate solution to the POT problem in Oe(n2.5/Ε). The second method, Dual Extrapolation, achieves the computation complexity of Oe(n2/Ε), thereby being the best in the literature. We further demonstrate the flexibility of POT compared to standard OT as well as the practicality of our algorithms on real applications where two marginal distributions are unbalanced. Copyright © 2024, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Gradient methods

ModelPred: A Framework for Predicting Trained Model from Training Data

学校读者我要写书评

暂无评论

ModelPred: A Framework for Predicting Trained Model from Tra...

Secure and Trustworthy Machine Learning (SaTML), IEEE Conference on

作者： Yingyan Zeng Jiachen T. Wang Si Chen Hoang Anh Just Ran Jin Ruoxi Jia Grado Department of Industrial and Systems Engineering Virginia Tech Blacksburg USA Department of Electrical and Computer Engineering Princeton University Princeton USA Bradley Department of Electrical and Computer Engineering Virginia Tech Blacksburg USA

In this work, we propose ModelPred, a framework that helps to understand the impact of changes in training data on a trained model. This is critical for building trust in various stages of a machine learning pipeline: from cleaning poor-quality samples and tracking important ones to be collected during data preparation, to calibrating uncertainty of model prediction, to interpreting why certain behaviors of a model emerge during deployment. Specifically, ModelPred learns a parameterized function that takes a dataset S as the input and predicts the model obtained by training on S. Our work differs from the recent work of Datamodels [1] as we aim for predicting the trained model parameters directly instead of the trained model behaviors. We demonstrate that a neural network-based set function class is capable of learning the complex relationships between the training data and model parameters. We introduce novel global and local regularization techniques to prevent overfitting and we rigorously characterize the expressive power of neural networks (NN) in approximating the end-to-end training process. Through extensive empirical investigations, we show that ModelPred enables a variety of applications that boost the interpretability and accountability of machine learning (ML), such as data valuation, data selection, memorization quantification, and model calibration.

关键词：

Neuromimetic Dynamic Networks with Hebbian Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sun, Zexin Baillieul, John The Division of Systems Engineering Boston University BostonMA02215 United States The Departments of Mechanical Engineering Electrical and Computer Engineering The Division of Systems Engineering Boston University BostonMA02215 United States

Leveraging recent advances in neuroscience and control theory, this paper presents a neuromimetic network model with dynamic symmetric connections governed by Hebbian learning rules. Formal analysis grounded in graph theory and classical control establishes that this biologically plausible model exhibits boundedness, stability, and structural controllability given a generalized sym-cactus structure with multiple control nodes. We prove the necessity of this topology when there are distributed control inputs. Simulations using a 14-node generalized sym-cactus network with two input types validate the model’s effectiveness in capturing key neural dynamics. © 2023, CC BY-NC-SA.

关键词： Graph theory

On de Bruijn Array Codes, Part II: Linear Codes

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chee, Yeow Meng Etzion, Tuvi Lao, Huimin Department of Industrial Systems Engineering and Management National University of Singapore Singapore Computer Science Department Technion Israel Institute of Technology Haifa3200003 Israel Department of Electrical and Computer Engineering National University of Singapore Singapore

An M-sequence generated by a primitive polynomial has many interesting and desirable properties. A pseudorandom array is the two-dimensional generalization of an M-sequence. Similarly to primitive polynomials, there are irreducible and reducible polynomials whose all nonzero sequences have the same length. In this paper, a two-dimensional generalization for such sequences is given. This generalization is for a pseudo-random array code which is a set of r1×r2 arrays in which each n1×n2 nonzero matrix is contained exactly once as a window in one of the arrays. Moreover, these arrays have the shift-and-add property, i.e., the bitwise addition of two arrays (or a nontrivial shift of such arrays) is another array (or a shift of another array) from the code. All the known arrays can be formed by folding sequences generated from an irreducible polynomial or a reducible polynomial whose factors have the same degree and the same exponent. Two proof techniques are used to prove the parameters of the constructed arrays. The first one is based on another method for constructing some of these arrays. The second one is a generalization of a known proof technique. This generalization enables to present pseudo-random arrays with parameters not known before and also a variety of pseudo-random array codes which cannot be generated by the first method. The two techniques also suggest two different hierarchies between pseudo-random array codes. Finally, a method to verify whether a folding of sequences, generated by these polynomials, yields a pseudo-random array or a pseudo-random array code, will be presented. © 2025, CC BY.

关键词： Polynomials